interscript 0.1.2 → 0.1.7

data/maps/odni-mkd-Cyrl-Latn-2015.yaml

@@ -0,0 +1,122 @@
+---
+authority_id: odni
+id: 2015
+language: iso-639-2:mkd
+source_script: Cyrl
+destination_script: Latn
+name: Standards for the transliteration of macedonian personal names in written reports and products
+source: ICS-630-01 Annex H
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community (IC) standard for the transliteration of Macedonian
+  names that will be applied to all final written reports and products for IC consumers. It is not
+  intended to eliminate variations of a name that can contribute forensic information. Rather, it is
+  to provide an IC standard Romanized (English) transliteration from Macedonian that can then be
+  linked to forensic information in ways that will help identify the referent of the name.
+
+  In cases where an individual’s name has already been transliterated in a variant spelling, the IC
+  Standard spelling should appear first, followed by the variant spelling(s) in parentheses at the
+  first usage. In addition, if the original Cyrillic spelling is known, that spelling should also
+  appear in parentheses following the name, if possible, following best practices of the issuing
+  organization and taking into consideration information system capabilities. This convention is
+  designed to ensure that vital forensic information is not lost.
+
+  For names of persons who are known to not be part of the Macedonian-speaking community, use the
+  relevant IC transliteration standard for names from that language (e.g., Mikhail, Yitzhak).
+  A translator’s note may be used to clarify the known origin of the person. Spell names of
+  individuals from languages that are written in Roman letters as they are spelled in those
+  languages (e.g., George Clooney, Jorge Garcia, Georges Pompidou).
+
+  In the case of active senior government officials in the on-line CIA World Factbook and the on-
+  line directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings given
+  in these on-line reference works should be used in place of the IC Standard. For any individual
+  who has at one time been listed in the Factbook or Chiefs of State directory but who no longer
+  appears in those resources (i.e. is no longer a government official), the IC Standard spelling
+  should appear first, with the spelling, if known, as it previously appeared in those resources
+  listed within parentheses at the first usage.
+
+  The primary goal is to produce a consistent Romanized transcription of names that is specifically
+  readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
+  (English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use of
+  diacritics. However, within the context of a report, where additional information about the
+  individual is provided, the referent will be clearly identified. This system will be used in
+  conjunction with on-line tools, name dictionaries, and lists containing conventional spellings of
+  names of well-known individuals.
+
+tests:
+  - source: Билјана
+    expected: Biljana
+  - source: Душко
+    expected: Dushko
+
+map:
+  rules:
+    - pattern: \u0053 # S => Dz
+      result: Dz
+    - pattern: \u0073 # s => dz
+      result: dz
+
+  characters:
+    '\u0410': 'A'     # А
+    '\u0411': 'B'     # Б
+    '\u0412': 'V'     # В
+    '\u0413': 'G'     # Г
+    '\u0414': 'D'     # Д
+    '\u0403': 'Gj'    # Ѓ
+    '\u0415': 'E'     # Е
+    '\u0416': 'Zh'    # Ж
+    '\u0417': 'Z'     # З
+    '\u0418': 'I'     # И
+    '\u0408': 'J'     # Ј
+    '\u041A': 'K'     # К
+    '\u041B': 'L'     # Л
+    '\u0409': 'Lj'    # Љ
+    '\u041C': 'M'     # М
+    '\u041D': 'N'     # Н
+    '\u040A':  Nj     # Њ
+    '\u041E': 'O'     # О
+    '\u041F': 'P'     # П
+    '\u0420': 'R'     # Р
+    '\u0421': 'S'     # С
+    '\u0422': 'T'     # Т
+    '\u040C': 'Kj'    # Ќ
+    '\u0423': 'U'     # У
+    '\u0424': 'F'     # Ф
+    '\u0425': 'H'     # Х
+    '\u0426': 'Ts'    # Ц
+    '\u0427': 'Ch'    # Ч
+    '\u040F': 'Dzh'   # Џ
+    '\u0428': 'Sh'    # Ш
+    '\u2019': ''      # ’
+
+    '\u0430': 'a'     # а
+    '\u0431': 'b'     # б
+    '\u0432': 'v'     # в
+    '\u0433': 'g'     # г
+    '\u0434': 'd'     # д
+    '\u0453': 'gj'    # ѓ
+    '\u0435': 'e'     # e
+    '\u0436': 'zh'    # ж
+    '\u0437': 'z'     # з
+    '\u0438': 'i'     # и
+    '\u0458': 'j'     # ј
+    '\u043A': 'k'     # к
+    '\u043B': 'l'     # л
+    '\u0459': 'lj'    # љ
+    '\u043C': 'm'     # м
+    '\u043D': 'n'     # н
+    '\u045A': 'nj'    # њ
+    '\u043E': 'o'     # о
+    '\u043F': 'p'     # п
+    '\u0440': 'r'     # р
+    '\u0441': 's'     # с
+    '\u0442': 't'     # т
+    '\u045C': 'kj'    # ќ
+    '\u0443': 'u'     # у
+    '\u0444': 'f'     # ф
+    '\u0445': 'h'     # х
+    '\u0446': 'ts'    # ц
+    '\u0447': 'ch'    # ч
+    '\u045F': 'dzh'   # џ
+    '\u0448': 'sh'    # ш

data/maps/odni-per-Arab-Latn-2015.yaml

@@ -0,0 +1,228 @@
+---
+authority_id: odni
+id: 2015
+language: iso-639-3:prs
+source_script: Arab
+destination_script: Latn
+name: ODNI Persian Farsi Dari Personal Names 2015 System, ICS-630-01 Annex J
+url: https://github.com/interscript/ics-630-01/blob/master/reference-docs/ANNEX%20J%20-%20Persian-Farsi_Dari_Personal_Names_FLTS_2018_Revision%20(U).pdf
+creation_date: 2015
+confirmation_date: 2015-11
+description: |
+  This system is the Intelligence Community (IC) standard for
+  the transliteration of Persian (Farsi)
+  and Dari names that is applied to all final written reports
+  and products for IC consumers. It is not
+  intended to eliminate variations of a name that can
+  contribute forensic information. Rather, it is
+  to provide an IC standard Romanized (English)
+  transliteration from Persian (Farsi) and Dari that
+  can then be linked to forensic information in ways that
+  will help identify the referent of the
+  name.
+
+  In cases where an individual’s name has already been
+  transliterated in a variant spelling, the IC
+  Standard spelling should appear first, followed by the
+  variant spelling(s) in parentheses at the
+  first usage. In addition, if the original Perso-Arabic
+  script spelling is known, that spelling should
+  also appear in parentheses following the name, if possible,
+  following best practices of the issuing
+  organization and taking into consideration information
+  system capabilities. This convention is
+  designed to ensure that vital forensic information is not
+  lost while maintaining consistency.
+
+  For names of individuals who are not part of the Persian-(
+  Farsi) or Dari-speaking community,
+  but whose names are encountered in Farsi or Dari, use the
+  relevant IC transliteration standard for
+  names from that language (e.g., Mikhail, Yitzhak, Abu-
+  Murtada). Spell names of individuals
+  from languages that are written in Roman letters as they
+  are spelled in those languages (e.g.,
+  George Clooney, Jorge Garcia, Georges Pompidou).
+  In the case of active senior government officials in the
+  online CIA World Factbook and the
+  online directory of Chiefs of State and Cabinet Members of
+  Foreign Governments, the spellings
+  given in these online reference works should be used in
+  place of the IC Standard, with the IC
+  Standard included as a variant in parentheses at the first
+  usage. For any individual who has at one
+  time been listed in the Factbook or Chiefs of State
+  directory but who no longer appears in those
+  resources (i.e., is no longer a government official), the
+  IC Standard spelling should appear first,
+  with the spelling, if known, as it previously appeared in
+  those resources listed within parentheses
+  at the first usage (e.g., former president Mahmud
+  Ahmadinezhad (Ahmadi-Nejad).
+
+  The primary goal is to produce a consistent Romanized
+  transcription of names that is specifically
+  readable to the English-speaking non-specialist. The system
+  uses the 26 letters of the standard
+  (English) Roman alphabet plus the apostrophe and hyphen.
+  Some ambiguities in the Romanized
+  form will occur without the use of diacritics. However,
+  within the context of a report, where
+  additional information about the individual is provided,
+  the referent will be clearly identified.
+  This system will be used in conjunction with online tools,
+  name dictionaries, and lists containing
+  conventional spellings of names of well-known individuals.
+
+notes:
+  - |
+    This standard is intended only for those Afghan names that
+    have a common bond or similarity with Iranian names. It
+    should not, for example, be used for names of Pashtuns, for
+    which the Pashto IC Standard should be used.
+
+  - |
+    Alef maqsura (final yeh pronounced as “a”): should be written “a” as in
+    “Musa”.
+
+  - |
+    Digraphs: No distinction is drawn between digraphs
+    such as sh and single contiguous letters (e.g., s followed
+    by h).
+
+  - |
+    Long/short vowels: There is no distinction made in
+    Roman between long and short a: E.g., Farhad (first a is
+    short, second is long).
+
+  - |
+    Diphthongs: Diphthongs are written ei and ow respectively:
+    Hosein; Khosrow.
+
+  - |
+    Double consonants: Double consonants represented by the
+    tashdid are shown by doubling the
+    Roman letter: Mo'azzami, Tavakkoli, Sajjad. Exceptions: Ein
+    and consonants represented by
+    Roman digraphs (e.g., sh, ch) are not doubled (Mobasher,
+    not Mobashsher). Double letters
+    are only used for tashdid (Hosein, not Hossein) or to
+    reflect “sun-letter” assimilation (see
+    below). Special care should be taken when possible to
+    discriminate between doubled and
+    non-doubled letters in names that are otherwise
+    indistinguishable in their transliterated forms:
+    Hasan (حسن (vs. Hassan (حسان(
+
+  - |
+    Compound first names will be written as distinct words:
+    Ali Reza (not Alireza or Ali-Reza);
+    Mohammad Hosein (not Mohammadhosein or Mohammad-Hosein),
+    with the exception of cases identified below.
+
+  - |
+    Arabic-origin names that incorporate the word “Allah” are
+    transliterated as one word, with the letter ‘o’ replacing the
+    alef in Allah (Azizollah, Rahimollah).
+
+  - |
+    Name-internal Arabic definite article "al" (‫)ال‬: Common
+    in many names borrowed
+    from Arabic, the transliteration should follow the Arabic
+    rules for “sun letter” assimilation in spoken form and
+    reflect the nominative case. That is: Abdorrahman, not Abd-
+    al-Rahman. (The Arabic sun letters are: ‫ت‬،‫ث‬،‫د‬،‫ذ‬،
+    ‫ر‬، ‫ز‬،‫س‬،‫ش‬،‫ص‬،‫ض‬،‫ط‬،‫ظ‬،‫ل‬،‫ن‬ . These correspond with
+    d, l, n, r, s, sh, t, and z.) Note that the moon letters (
+    i.e., all other Arabic letters) are not assimilated (e.g.,
+    Abdolhasan, Abolfazl). Note also that the “Abdollah” and
+    “Abdol + attribute of Allah” names are written as a single
+    word, as are other names that contain the definite article:
+    Shamsoddin (not Shams-al-Din), Nezamoddin, etc.
+
+  - |
+    Name-initial Arabic definite article "al" (‫)ال‬: For
+    Arabic-origin names starting with the definite article “al” (‫)
+    ال‬, follow the Arabic standard of al-Sisi (‫)الصیصی‬ (not
+    Alsisi or Assisi) and forego sun-letter assimilation.
+
+  - |
+    Arabic "family marker" of Al (‫)آل‬: For Arabic-origin
+    names starting with the "family marker" of Al (‫)آل‬,
+    follow the Arabic standard of Al Davud (‫داود‬ ‫)آل‬ (not
+    Aldavud or Aledavud).
+
+  - |
+    Kunyas: In the rather rare case where
+    a Persian uses a kunya (a name for an adult normally
+    derived from his or her eldest child, and sometimes
+    employed as a nom de guerre), this name will be rendered
+    with a space separating the two elements (Abu Hosein, Abu
+    Ghasem). Note that this does not apply when the person's
+    given or family name was derived from a predecessor's
+    kunya. In these cases, the leading element should be
+    treated as a prefix as indicated below (Abuhosein[i],
+    Abughasem[i]).
+
+tests:
+  - source: مُوسَى
+    expected: musa
+
+  - source: مُؤمِن
+    expected: momen
+
+  - source: رِضايي
+    expected: rezai
+
+  - source: مُبَشِّر
+    expected: mobasher
+
+  - source: حَسَّان
+    expected: hassan
+
+  - source: حَسَن
+    expected: hasan
+
+  - source: صَفَّار
+    expected: saffar
+
+  - source: صَفَر
+    expected: safar
+
+map:
+  inherit: odni-fas-Arab-Latn-2015
+  characters:
+
+    # ta' marboota
+    '\u0629' : 'ah'
+
+    '\u0626' : '' # ئ
+    '\u0624' : '' # ؤ
+
+    # Farsi Vowel (Pointing)
+
+    # '\u064e\u0648' : 'ow'  # ـَو
+    # '\u064e\u0648\u0652' : 'aw'  # ـَوْ
+
+    # additional symbols
+
+    # shadda
+
+    '\u0642\u0651' : 'qq'  # ق
+    '\u0648\u0651' : 'ww'  # و
+
+    '\u0621': '' # ء
+
+    # FROM NOTES
+
+    '\u064a\u064a' : 'i' # NOTE 4 (2)
+    '\u06cc\u06cc' : 'i'
+
+    '\u0627\u064a\b' : 'i' # NOTE 4 (3)
+    '\u0627\u06cc\b' : 'i'
+
+    # Farsi consonant characters
+
+    '\u0639' : ''  # ع # new
+    '\u0642' : 'q'  # ق
+    '\u0648' : 'w'  # و

data/maps/odni-rus-Cyrl-Latn-2015.yaml

@@ -0,0 +1,77 @@
+---
+authority_id: odni
+id: 2015
+language: iso-639-2:rus
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Russian Personal Names 2015, ICS-630-01 Annex K
+# url:
+source: ICS-630-01 Annex K
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system, adapted from the Board of Geographic Names (BGN) Romanization system for Russian
+  (1947), is the Intelligence Community (IC) standard for the transliteration of Russian names that will be
+  applied to all final written reports and products for IC consumers. It is not intended to eliminate variations
+  of a name that can contribute forensic information. Rather, it is to provide an IC standard Romanized
+  (English) transliteration from Russian that can then be linked to forensic information in ways that will
+  help identify the referent of the name.
+
+  In cases where an individual’s name has already been transliterated in a variant spelling, the IC Standard
+  spelling should appear first, followed by the variant spelling(s) in parentheses at the first usage. E.g.,
+  Sergey Nikolayevich Tyurin (Serguei Nicolaivitch Tiourine). In addition, if the original Cyrillic spelling
+  is known, that spelling should also appear in parentheses following the name, if possible, following best
+  practices of the issuing organization and taking into consideration information system capabilities. This
+  convention is designed to ensure that vital forensic information is not lost.
+
+  For non-Russian names, use the relevant IC transliteration standard for names from that language. A
+  translator’s note may be used to clarify the known origin of the person. Spell names of individuals from
+  languages that are written in Roman letters as they are spelled in those languages (e.g., George Clooney,
+  Jorge Garcia, Georges Pompidou).
+
+  In the case of active senior government officials in the on-line CIA World Factbook and the on-line
+  directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings given in these
+  on-line reference works should be used in place of the IC Standard. For any individual who has at one
+  time been listed in the Factbook or Chiefs of State directory but who no longer appears in those resources
+  (i.e. is no longer a government official), the IC Standard spelling should appear first, with the spelling, if
+  known, as it previously appeared in those resources listed within parentheses at the first usage.
+
+  The primary goal is to produce a consistent Romanized transcription of names that is specifically readable
+  to the English-speaking non-specialist. The system uses the 26 letters of the standard (English) Roman
+  alphabet. Some ambiguities in the Romanized form will occur without the use of diacritics. However,
+  within the context of a report, where additional information about the individual is provided, the referent
+  will be clearly identified. This system will be used in conjunction with on-line tools, name dictionaries,
+  and lists containing conventional spellings of names of well-known individuals.
+
+notes:
+
+tests:
+  - source: Ирина Ивановна Никитина
+    expected: Irina Ivanovna Nikitina
+  - source: Николай Римский-Корсаков
+    expected: Nikolay Rimskiy-Korsakov
+  - source: Михаил Тимофеевич Калашников
+    expected: Mikhail Timofeyevich Kalashnikov
+  - source: Корж Василий Захарович
+    expected: Korzh Vasiliy Zakharovich
+  - source: Циолковский Константин Эдуардович
+    expected: Tsiolkovskiy Konstantin Eduardovich
+  - source: Лобачевский Николай Иванович
+    expected: Lobachevskiy Nikolay Ivanovich
+  - source: Пушкин Александр Сергеевич
+    expected: Pushkin Aleksandr Sergeyevich
+  - source: Гоголь Николай Васильевич
+    expected: Gogol Nikolay Vasilyevich
+  - source: Ломоносов Михаил Васильевич
+    expected: Lomonosov Mikhail Vasilyevich
+
+map:
+  inherit: bgnpcgn-rus-Cyrl-Latn-1947
+
+  characters:
+    '\u042a': '' # Ъ
+    '\u042c': '' # Ь
+
+
+    '\u044a': '' # ъ
+    '\u044c': '' # ь

data/maps/odni-srp-Cyrl-Latn-2015.yaml

@@ -0,0 +1,129 @@
+---
+authority_id: odni
+id: 2015
+language: iso-639-2:srp
+source_script: Cyrl
+destination_script: Latn
+name: Office of the Director Of National Intelligence Serbian Personal Names 2015, ICS-630-01 Annex L
+# url:
+source: ICS-630-01 Annex L
+creation_date: 2015
+confirmation_date: 2015
+description: |
+  This system is the Intelligence Community (IC) standard for the transliteration of Serbian names
+  written in Cyrillic that will be applied to all final written reports and products for IC consumers. It
+  is not intended to eliminate variations of a name that can contribute forensic information. Rather,
+  it is to provide an IC standard Romanized (English) transliteration from Serbian that can then be
+  linked to forensic information in ways that will help identify the referent of the name.
+
+  In cases where an individual’s name has already been transliterated in a variant spelling, the IC
+  Standard spelling should appear first, followed by the variant spelling(s) in parentheses at the first
+  usage. In addition, if the original Cyrillic spelling is known, that spelling should also appear in
+  parentheses following the name, if possible, following best practices of the issuing organization
+  and taking into consideration information system capabilities. This convention is designed to
+  ensure that vital forensic information is not lost.
+
+  For names of persons who are known to not be part of the Serbian-speaking community, use the
+  relevant IC transliteration standard for names from that language (e.g., Mikhail, Yitzhak). A
+  translator’s note may be used to clarify the known origin of the person. Spell names of
+  individuals from languages that are written in Roman letters as they are spelled in those
+  languages (e.g., George Clooney, Jorge Garcia, Georges Pompidou).
+
+  In the case of active senior government officials in the on-line CIA World Factbook and the online directory of Chiefs of State and Cabinet Members of Foreign Governments, the spellings
+  given in these on-line reference works should be used in place of the IC Standard. For any
+  individual who has at one time been listed in the Factbook or Chiefs of State directory but who no
+  longer appears in those resources (i.e. is no longer a government official), the IC Standard
+  spelling should appear first, with the spelling, if known, as it previously appeared in those
+  resources listed within parentheses at the first usage.
+
+  The primary goal is to produce a consistent Romanized transcription of names that is specifically
+  readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
+  (English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use
+  of diacritics. However, within the context of a report, where additional information about the
+  individual is provided, the referent will be clearly identified. This system will be used in
+  conjunction with on-line tools, name dictionaries, and lists containing conventional spellings of
+  names of well-known individuals.
+
+notes:
+
+tests:
+  - source: Гојко Митић
+    expected: Gojko Mitic
+  - source: Горња Ваганица
+    expected: Gornja Vaganica
+  - source: Довиђења
+    expected: Dovidjenja
+  - source: Ћао! Здраво!
+    expected: Cao! Zdravo!
+  - source: Кључ
+    expected: Kljuc
+  - source: Цигарете
+    expected: Cigarete
+  - source: Пролеће
+    expected: Prolece
+  - source: Понедељак
+    expected: Ponedeljak
+
+map:
+  characters:
+    '\u0410': 'A'  # А
+    '\u0411': 'B'  # Б
+    '\u0412': 'V'  # В
+    '\u0413': 'G'  # Г
+    '\u0414': 'D'  # Д
+    '\u0402': 'Dj' # Ђ
+    '\u0415': 'E'  # Е
+    '\u0416': 'Z'  # Ж
+    '\u0417': 'Z'  # З
+    '\u0418': 'I'  # И
+    '\u0408': 'J'  # Ј
+    '\u041A': 'K'  # К
+    '\u041B': 'L'  # Л
+    '\u0409': 'Lj' # Љ
+    '\u041C': 'M'  # М
+    '\u041D': 'N'  # Н
+    '\u040A':  Nj  # Њ
+    '\u041E': 'O'  # О
+    '\u041F': 'P'  # П
+    '\u0420': 'R'  # Р
+    '\u0421': 'S'  # С
+    '\u0422': 'T'  # Т
+    '\u040B': 'C'  # Ћ
+    '\u0423': 'U'  # У
+    '\u0424': 'F'  # Ф
+    '\u0425': 'H'  # Х
+    '\u0426': 'C'  # Ц
+    '\u0427': 'C'  # Ч
+    '\u040F': 'Dz' # Џ
+    '\u0428': 'S'  # Ш
+
+    '\u0430': 'a'  # а
+    '\u0431': 'b'  # б
+    '\u0432': 'v'  # в
+    '\u0433': 'g'  # г
+    '\u0434': 'd'  # д
+    '\u0452': 'dj' # ђ
+    '\u0435': 'e'  # e
+    '\u0436': 'z'  # ж
+    '\u0437': 'z'  # з
+    '\u0438': 'i'  # и
+    '\u0458': 'j'  # ј
+    '\u043A': 'k'  # к
+    '\u043B': 'l'  # л
+    '\u0459': 'lj' # љ
+    '\u043C': 'm'  # м
+    '\u043D': 'n'  # н
+    '\u045A': 'nj' # њ
+    '\u043E': 'o'  # о
+    '\u043F': 'p'  # п
+    '\u0440': 'r'  # р
+    '\u0441': 's'  # с
+    '\u0442': 't'  # т
+    '\u045B': 'c'  # ћ
+    '\u0443': 'u'  # у
+    '\u0444': 'f'  # ф
+    '\u0445': 'h'  # х
+    '\u0446': 'c'  # ц
+    '\u0447': 'c'  # ч
+    '\u045F': 'dz' # џ
+    '\u0448': 's'  # ш